© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37164
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate measurement or frequency related to data statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    611
    +0.11
    0.5%
    690
    +0.10
    0.5%
    593
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    611
    +0.11
    0.04
    362
    +0.10
    0.04
    593
    +0.09
    0.03
    Negative Logits
    kat
    -0.74
    uyomi
    -0.71
    ä¹ĭ
    -0.70
     rul
    -0.68
    soType
    -0.68
    äºĶ
    -0.68
    女
    -0.68
    çİĭ
    -0.68
    idad
    -0.67
    uristic
    -0.67
    POSITIVE LOGITS
     sorts
    0.87
     any
    0.78
     course
    0.77
     each
    0.71
     those
    0.69
     incumb
    0.67
     ANY
    0.67
     competitors
    0.66
    avorite
    0.65
    ortunately
    0.64
    Activations Density 0.151%

    No Known Activations